首页> 美国政府科技报告 >Support Vector Machines Applied to Face Recognition
【24h】

Support Vector Machines Applied to Face Recognition

机译:支持向量机在人脸识别中的应用

获取原文

摘要

Face recognition is a K class problem, where K is the number of known211u001eindividuals; and support vector machines (SVMs) are a binary classification 211u001emethod, By reformulating the face recognition problem and re-interpreting the 211u001eoutput of the SVM classifier, the authors developed a SVM-based face recognition 211u001ealgorithm. The face recognition problem is formulated as a problem in difference 211u001espace, which models dissimilartities between faces of the same person, and 211u001edissimilarities between faces of different people. By modifying the 211u001einterpretation of the decision surface generated by SVM, the authors generated a 211u001esimilarity metric between faces that is learned from examples of differences 211u001ebetween faces. The SVM-based algorithm is compared with a principal component 211u001eanalysis (PCA) based algorithm on a difficult set of images from the FERET 211u001edatabase. Performance was measured for both verification and identification 211u001escenarios.

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号